Claude Skills by michalekz

Playbook for a Claude Code agent in the role of orchestrator of 2-N worker peers over the claude-bridge MCP. Use when you have a team of peers and want to efficiently dispatch tasks, gate outputs, resolve conflicts, protect invariants, route memory, and hold the interface to the human owner. Triggers — "I'm the manager agent", "I'm orchestrating a team of peers", "I'm running worker chats", "dispatch a task to peers", "gate workflow", "managing agent role", multi-peer orchestration.

Playbook for a Claude Code agent in the dedicated memory keeper role — single-writer for shared agent memory across a team of 3+ peers. Use when you are designated as the keeper (= other peers send you write candidates, you write them and watch for drift). Memory hygiene + reconciliation against the canon + drift detection. Triggers — "I'm the memory keeper", "memory hygiene", "shared memory", "reconcile memory", "single-writer keeper".

Guide the user through activating claude-bridge live-data hooks in ~/.claude/settings.json. Use when the user asks how to install the plugin's statusLine wrapper or PostToolUse refresh-limits hook, or when peer_context_status / rate_limit_status returns `hasLiveData: false` with a setupPointer. Triggers — "setup live data", "install claude-bridge hooks", "hasLiveData false", "how do I activate statusLine wrapper", "setupPointer says", "peer_context_status returns no data".

Use when orchestrating multiple Claude Code chats, reading other chats' history, sending messages between chats, or searching across chat sessions. Triggers on phrases like "peer chat", "sister chat", "other chat", "cross-chat", "what is the other agent doing", "find in chats", "manager agent", "worker agent", "agent-to-agent communication", and similar multi-chat coordination requests.